Box Plot Example

A box plot summarizes a distribution of quantitative values using a set of summary statistics. Here, the boxes show the interquartile range (IQR), with the white bar indicating the median value. The thin lines (“whiskers”) currently show the extent of the minimum and maximum values; other values, such as whiskers extending 1.5 * IQR from each end of the box, are often used as well. See the violin plot example for an alternative approach.

Vega JSON Specification <>

{
  "$schema": "https://vega.github.io/schema/vega/v5.json",
  "description": "A box plot example showing aggregate statistics for penguin body mass.",
  "width": 500,
  "padding": 5,

  "config": {
    "axisBand": {
      "bandPosition": 1,
      "tickExtra": true,
      "tickOffset": 0
    }
  },

  "signals": [
    { "name": "plotWidth", "value": 60 },
    { "name": "height", "update": "(plotWidth + 10) * 3"}
  ],

  "data": [
    {
      "name": "penguins",
      "url": "data/penguins.json",
      "transform": [
        {
          "type": "filter",
          "expr": "datum.Species != null && datum['Body Mass (g)'] != null"
        }
      ]
    }
  ],

  "scales": [
    {
      "name": "layout",
      "type": "band",
      "range": "height",
      "domain": {"data": "penguins", "field": "Species"}
    },
    {
      "name": "xscale",
      "type": "linear",
      "range": "width", "round": true,
      "domain": {"data": "penguins", "field": "Body Mass (g)"},
      "domainMin": 2000,
      "zero": false, "nice": true
    }
  ],

  "axes": [
    {"orient": "bottom", "scale": "xscale", "zindex": 1},
    {"orient": "left", "scale": "layout", "tickCount": 5, "zindex": 1}
  ],

  "marks": [
    {
      "type": "group",
      "from": {
        "facet": {
          "data": "penguins",
          "name": "species",
          "groupby": "Species"
        }
      },

      "encode": {
        "enter": {
          "yc": {"scale": "layout", "field": "Species", "band": 0.5},
          "height": {"signal": "plotWidth"},
          "width": {"signal": "width"}
        }
      },

      "data": [
        {
          "name": "summary",
          "source": "species",
          "transform": [
            {
              "type": "aggregate",
              "fields": ["Body Mass (g)", "Body Mass (g)", "Body Mass (g)", "Body Mass (g)", "Body Mass (g)"],
              "ops": ["min", "q1", "median", "q3", "max"],
              "as": ["min", "q1", "median", "q3", "max"]
            }
          ]
        }
      ],

      "marks": [
        {
          "type": "rect",
          "from": {"data": "summary"},
          "encode": {
            "enter": {
              "fill": {"value": "black"},
              "height": {"value": 1}
            },
            "update": {
              "yc": {"signal": "plotWidth / 2", "offset": -0.5},
              "x": {"scale": "xscale", "field": "min"},
              "x2": {"scale": "xscale", "field": "max"}
            }
          }
        },
        {
          "type": "rect",
          "from": {"data": "summary"},
          "encode": {
            "enter": {
              "fill": {"value": "steelblue"},
              "cornerRadius": {"value": 4}
            },
            "update": {
              "yc": {"signal": "plotWidth / 2"},
              "height": {"signal": "plotWidth / 2"},
              "x": {"scale": "xscale", "field": "q1"},
              "x2": {"scale": "xscale", "field": "q3"}
            }
          }
        },
        {
          "type": "rect",
          "from": {"data": "summary"},
          "encode": {
            "enter": {
              "fill": {"value": "aliceblue"},
              "width": {"value": 2}
            },
            "update": {
              "yc": {"signal": "plotWidth / 2"},
              "height": {"signal": "plotWidth / 2"},
              "x": {"scale": "xscale", "field": "median"}
            }
          }
        }
      ]
    }
  ]
}